INDEX

Explanations

Places/locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĮĸ

-0.27

æķĪåºĶ

-0.27

say

-0.26

shift

-0.26

çĹħæ¯ĴæĦŁæŁĵ

-0.25

hift

-0.25

ivalence

-0.25

mother

-0.25

say

-0.25

Tie

-0.24

POSITIVE LOGITS

å¹³åĿĩæ°´å¹³

0.29

	tests

0.27

||(

0.25

 schedules

0.25

 solicit

0.25

ouce

0.24

 excuses

0.24

 tests

0.24

lux

0.24

chaft

0.24

Activations Density 0.002%

Places/locations

No Comments

No Known Activations